© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22132
    Prev
    Next
    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    conds
    -0.28
    ä¸Ģè§Ī
    -0.28
    Ļ¨
    -0.26
    è¨ĪåĬĥ
    -0.25
    å±IJ
    -0.25
    çĽ²
    -0.25
    çł´è£Ĥ
    -0.24
    åѵ
    -0.23
    oust
    -0.23
    (plan
    -0.23
    POSITIVE LOGITS
    ilen
    0.26
    ergy
    0.26
    æĪij个人
    0.25
    à¤ĸ
    0.25
     ole
    0.24
     il
    0.24
    æĪijè¿ĺæĺ¯
    0.24
    ole
    0.24
    庸
    0.24
     Attention
    0.23
    Activations Density 0.006%

    No Known Activations